{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:40:29Z","timestamp":1775324429709,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533923","type":"print"},{"value":"9789819533930","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-3393-0_20","type":"book-chapter","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T09:51:00Z","timestamp":1761904260000},"page":"243-254","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Supplementary Information for\u00a0First-Person Perception Referring Expression Comprehension"],"prefix":"10.1007","author":[{"given":"Zetao","family":"Du","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhepeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,1]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Akbari, H., Karaman, S., Bhargava, S., Chen, B., Vondrick, C., Chang, S.F.: Multi-level multimodal common semantic space for image-phrase grounding. In: Proceedings of the IEEE\/CVF CVPR, pp. 12476\u201312486 (2019)","DOI":"10.1109\/CVPR.2019.01276"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Chen, S., Luo, G., Zhou, Y., Sun, X., Jiang, G., Ji, R.: QueryMatch: a query-based contrastive learning framework for weakly supervised visual grounding. In: Proceedings of the ACM MM, pp. 4177\u20134186 (2024)","DOI":"10.1145\/3664647.3681058"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE\/CVF CVPR, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Dai, M., Yang, L., Xu, Y., Feng, Z., Yang, W.: SIMVG: a simple framework for visual grounding with decoupled multi-modal fusion. arXiv preprint arXiv:2409.17531 (2024)","DOI":"10.52202\/079017-3867"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Yang, Z., Chen, T., Zhou, W., Li, H.: TRANSVG: end-to-end visual grounding with transformers. In: Proceedings of the IEEE\/CVF ICCV, pp. 1769\u20131779 (2021)","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"20_CR6","unstructured":"Grauman, K.,et\u00a0al.: EGO4D: around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF CVPR, pp. 18995\u201319012 (2022)"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Gupta, T., Vahdat, A., Chechik, G., Yang, X., Kautz, J., Hoiem, D.: Contrastive learning for weakly supervised phrase grounding. In: Proceedings of the ECCV, pp. 752\u2013768 (2020)","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"20_CR8","unstructured":"Henighan, T., et\u00a0al.: Scaling laws for autoregressive generative modeling. arXiv preprint arXiv:2010.14701 (2020)"},{"key":"20_CR9","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: Proceedings of the ICML, pp. 4904\u20134916. PMLR (2021)"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: MDETR-modulated detection for end-to-end multi-modal understanding. In: Proceedings of the IEEE\/CVF ICCV, pp. 1780\u20131790 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferitGame: referring to objects in photographs of natural scenes. In: Proceedings of the EMNLP, pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Korekata, R., et al.: Switching head-tail funnel UNITER for dual referring expression comprehension with fetch-and-carry tasks. In: Proceedings of the IROS, pp. 3865\u20133872 (2023)","DOI":"10.1109\/IROS55552.2023.10342165"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Kurita, S., Katsura, N., Onami, E.: REFEGO: referring expression comprehension dataset from first-person perception of EGO4D. In: Proceedings of the IEEE\/CVF ICCV, pp. 15214\u201315224 (2023)","DOI":"10.1109\/ICCV51070.2023.01396"},{"key":"20_CR14","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Proceedings of the ICML, pp. 12888\u201312900. PMLR (2022)"},{"key":"20_CR15","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. NeurIPS 34, 9694\u20139705 (2021)","journal-title":"NeurIPS"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF CVPR, pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Naseer, M., Khan, S., Porikli, F.: Indoor scene understanding in 2.5\/3D for autonomous agents: a survey. IEEE Access 7, 1859\u20131887 (2018)","DOI":"10.1109\/ACCESS.2018.2886133"},{"key":"20_CR19","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE\/CVF ICCV, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"20_CR21","doi-asserted-by":"publisher","first-page":"4426","DOI":"10.1109\/TMM.2020.3042066","volume":"23","author":"Y Qiao","year":"2020","unstructured":"Qiao, Y., Deng, C., Wu, Q.: Referring expression comprehension: a survey of methods and datasets. IEEE Trans. Multimedia 23, 4426\u20134440 (2020)","journal-title":"IEEE Trans. Multimedia"},{"key":"20_CR22","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: Proceedings of the ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"20_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1007\/978-3-319-46448-0_49","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Rohrbach","year":"2016","unstructured":"Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T., Schiele, B.: Grounding of textual phrases in images by reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 817\u2013834. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_49"},{"key":"20_CR24","unstructured":"Liu, R., et al.: ObjectFinder: open-vocabulary assistive system for interactive object search by blind people. arXiv:2412.03118 (2024)"},{"key":"20_CR25","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: Proceedings of the ICML, pp. 6105\u20136114. PMLR (2019)"},{"key":"20_CR26","unstructured":"Vaswani, A.: Attention is all you need. In: NeurIPS (2017)"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Wang, J., Specia, L.: Phrase localization without paired training examples. In: Proceedings of the IEEE\/CVF ICCV, pp. 4663\u20134672 (2019)","DOI":"10.1109\/ICCV.2019.00476"},{"key":"20_CR28","unstructured":"Wang, P., et al.: OFA: unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In: Proceedings of the ICML, pp. 23318\u201323340. PMLR (2022)"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Yan, B., et al.: Universal instance perception as object discovery and retrieval. In: Proceedings of the IEEE\/CVF CVPR, pp. 15325\u201315336 (2023)","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: MattNet: modular attention network for referring expression comprehension. In: Proceedings of the IEEE CVPR, pp. 1307\u20131315 (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"20_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3393-0_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T16:30:09Z","timestamp":1775320209000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3393-0_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"ISBN":["9789819533923","9789819533930"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3393-0_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,1]]},"assertion":[{"value":"1 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xuzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icig.csig.org.cn\/2025\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}